Claude Opus 4.7

anthropic/claude-4.7-opus-20260416

Claude Opus 4.7 is an Anthropic model that accepts text, image, and file inputs and generates text output. It supports tools and reasoning, handles a context length of 1,000,000 tokens, is not open‑source, and was released on 2026‑04‑16 with input pricing of $5 per M tokens and output pricing of $25 per M tokens.

tool use
structured outputs
reasoning

At a glance

provideranthropic

releasedAug 26, 2025

context1M

input / M$5

Specifications

What the API gives you

Context window: 1M tokens
Max output: 128K tokens
Input price: $5 / 1M tokens
Output price: $25 / 1M tokens
Cache read: $0.50 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: —
Released: Aug 26, 2025

Measured evidence

Public benchmark record

Design Arena Coding: 1318 Elo2026-07-28
Design Arena Coding: 1318 Elo2026-07-27
Design Arena Coding: 1318 Elo2026-07-30
Design Arena Coding: 1318 Elo2026-07-29
Design Arena Coding: 1318 Elo2026-07-31
Design Arena Coding: 1318 Elo2026-08-02
Design Arena Coding: 1318 Elo2026-08-05
Design Arena Coding: 1318 Elo2026-08-01
Design Arena Coding: 1317 Elo2026-08-09
Design Arena Coding: 1318 Elo2026-08-03
Design Arena Coding: 1318 Elo2026-08-04
Design Arena Coding: 1314 Elo2026-08-14
Design Arena Coding: 1318 Elo2026-08-06
Design Arena Coding: 1316 Elo2026-08-10
Design Arena Coding: 1318 Elo2026-08-07
Design Arena Coding: 1311 Elo2026-08-18
Design Arena Coding: 1317 Elo2026-08-08
Design Arena Coding: 1316 Elo2026-08-21
Design Arena Coding: 1310 Elo2026-08-15
Design Arena Coding: 1317 Elo2026-08-11
Design Arena Coding: 1316 Elo2026-08-12
Design Arena Coding: 1310 Elo2026-08-19
Design Arena Coding: 1315 Elo2026-08-13
Design Arena Coding: 1316 Elo2026-08-27
Design Arena Coding: 1307 Elo2026-09-05
Design Arena Coding: 1310 Elo2026-08-20
Design Arena Coding: 1310 Elo2026-08-16
Design Arena Coding: 1310 Elo2026-08-17
Design Arena Coding: 1316 Elo2026-08-22
Design Arena Coding: 1316 Elo2026-08-23
Design Arena Coding: 1315 Elo2026-08-28
Design Arena Coding: 1316 Elo2026-08-24
Design Arena Coding: 1316 Elo2026-08-25
Design Arena Coding: 1316 Elo2026-08-26
Design Arena Coding: 1307 Elo2026-09-06
Design Arena Coding: 1315 Elo2026-08-29
Design Arena Coding: 1315 Elo2026-08-30
Design Arena Coding: 1315 Elo2026-08-31
Design Arena Coding: 1315 Elo2026-09-01
Design Arena Coding: 1314 Elo2026-09-02
Design Arena Coding: 1312 Elo2026-09-03
Design Arena Coding: 1310 Elo2026-09-04
Design Arena Full-stack Agent: 1503 Elo2026-07-28
Design Arena Full-stack Agent: 1503 Elo2026-07-27
Design Arena Full-stack Agent: 1503 Elo2026-07-30
Design Arena Full-stack Agent: 1503 Elo2026-07-29
Design Arena Full-stack Agent: 1503 Elo2026-07-31
Design Arena Full-stack Agent: 1503 Elo2026-08-02
Design Arena Full-stack Agent: 1503 Elo2026-08-05
Design Arena Full-stack Agent: 1503 Elo2026-08-01
Design Arena Full-stack Agent: 1503 Elo2026-08-09
Design Arena Full-stack Agent: 1503 Elo2026-08-03
Design Arena Full-stack Agent: 1503 Elo2026-08-04
Design Arena Full-stack Agent: 1503 Elo2026-08-14
Design Arena Full-stack Agent: 1503 Elo2026-08-06
Design Arena Full-stack Agent: 1503 Elo2026-08-10
Design Arena Full-stack Agent: 1503 Elo2026-08-07
Design Arena Full-stack Agent: 1503 Elo2026-08-18
Design Arena Full-stack Agent: 1503 Elo2026-08-08
Design Arena Full-stack Agent: 1503 Elo2026-08-15
Design Arena Full-stack Agent: 1503 Elo2026-08-11
Design Arena Full-stack Agent: 1503 Elo2026-08-12
Design Arena Full-stack Agent: 1503 Elo2026-08-13
Design Arena Full-stack Agent: 1503 Elo2026-08-19
Design Arena Full-stack Agent: 1503 Elo2026-08-27
Design Arena Full-stack Agent: 1503 Elo2026-08-20
Design Arena Full-stack Agent: 1503 Elo2026-08-16
Design Arena Full-stack Agent: 1503 Elo2026-09-05
Design Arena Full-stack Agent: 1503 Elo2026-08-17
Design Arena Full-stack Agent: 1503 Elo2026-08-21
Design Arena Full-stack Agent: 1503 Elo2026-08-22
Design Arena Full-stack Agent: 1503 Elo2026-08-23
Design Arena Full-stack Agent: 1503 Elo2026-08-28
Design Arena Full-stack Agent: 1503 Elo2026-08-24
Design Arena Full-stack Agent: 1503 Elo2026-08-25
Design Arena Full-stack Agent: 1503 Elo2026-08-26
Design Arena Full-stack Agent: 1503 Elo2026-09-06
Design Arena Full-stack Agent: 1503 Elo2026-08-29
Design Arena Full-stack Agent: 1503 Elo2026-08-30
Design Arena Full-stack Agent: 1503 Elo2026-08-31
Design Arena Full-stack Agent: 1503 Elo2026-09-01
Design Arena Full-stack Agent: 1503 Elo2026-09-02
Design Arena Full-stack Agent: 1503 Elo2026-09-03
Design Arena Full-stack Agent: 1503 Elo2026-09-04
Design Arena UI: 1339 Elo2026-07-28
Design Arena UI: 1338 Elo2026-07-27
Design Arena UI: 1339 Elo2026-07-30
Design Arena UI: 1339 Elo2026-07-29
Design Arena UI: 1340 Elo2026-07-31
Design Arena UI: 1342 Elo2026-08-02
Design Arena UI: 1341 Elo2026-08-01
Design Arena UI: 1337 Elo2026-08-05
Design Arena UI: 1335 Elo2026-08-09
Design Arena UI: 1341 Elo2026-08-03
Design Arena UI: 1338 Elo2026-08-04
Design Arena UI: 1333 Elo2026-08-14
Design Arena UI: 1337 Elo2026-08-06
Design Arena UI: 1338 Elo2026-08-07
Design Arena UI: 1335 Elo2026-08-10
Design Arena UI: 1335 Elo2026-08-08
Design Arena UI: 1332 Elo2026-08-18
Design Arena UI: 1336 Elo2026-08-11
Design Arena UI: 1332 Elo2026-08-15
Design Arena UI: 1336 Elo2026-08-12
Design Arena UI: 1336 Elo2026-08-13
Design Arena UI: 1332 Elo2026-08-19
Design Arena UI: 1332 Elo2026-08-27
Design Arena UI: 1332 Elo2026-08-16
Design Arena UI: 1332 Elo2026-08-20
Design Arena UI: 1332 Elo2026-08-17
Design Arena UI: 1329 Elo2026-09-05
Design Arena UI: 1331 Elo2026-08-21
Design Arena UI: 1331 Elo2026-08-22
Design Arena UI: 1331 Elo2026-08-23
Design Arena UI: 1333 Elo2026-08-28
Design Arena UI: 1332 Elo2026-08-24
Design Arena UI: 1332 Elo2026-08-25
Design Arena UI: 1332 Elo2026-08-26
Design Arena UI: 1329 Elo2026-09-06
Design Arena UI: 1333 Elo2026-08-29
Design Arena UI: 1333 Elo2026-08-30
Design Arena UI: 1333 Elo2026-08-31
Design Arena UI: 1333 Elo2026-09-01
Design Arena UI: 1332 Elo2026-09-02
Design Arena UI: 1330 Elo2026-09-03
Design Arena UI: 1329 Elo2026-09-04
Design Arena Web-app Agent: 1305 Elo2026-07-28
Design Arena Web-app Agent: 1305 Elo2026-07-27
Design Arena Web-app Agent: 1303 Elo2026-07-30
Design Arena Web-app Agent: 1304 Elo2026-07-29
Design Arena Web-app Agent: 1303 Elo2026-07-31
Design Arena Web-app Agent: 1304 Elo2026-08-02
Design Arena Web-app Agent: 1303 Elo2026-08-01
Design Arena Web-app Agent: 1302 Elo2026-08-05
Design Arena Web-app Agent: 1296 Elo2026-08-09
Design Arena Web-app Agent: 1304 Elo2026-08-03
Design Arena Web-app Agent: 1304 Elo2026-08-04
Design Arena Web-app Agent: 1291 Elo2026-08-14
Design Arena Web-app Agent: 1302 Elo2026-08-06
Design Arena Web-app Agent: 1293 Elo2026-08-10
Design Arena Web-app Agent: 1302 Elo2026-08-07
Design Arena Web-app Agent: 1296 Elo2026-08-18
Design Arena Web-app Agent: 1302 Elo2026-08-08
Design Arena Web-app Agent: 1293 Elo2026-08-11
Design Arena Web-app Agent: 1295 Elo2026-08-15
Design Arena Web-app Agent: 1293 Elo2026-08-12
Design Arena Web-app Agent: 1292 Elo2026-08-13
Design Arena Web-app Agent: 1296 Elo2026-08-19
Design Arena Web-app Agent: 1279 Elo2026-08-27
Design Arena Web-app Agent: 1296 Elo2026-08-20
Design Arena Web-app Agent: 1299 Elo2026-08-16
Design Arena Web-app Agent: 1279 Elo2026-09-05
Design Arena Web-app Agent: 1299 Elo2026-08-17
Design Arena Web-app Agent: 1288 Elo2026-08-21
Design Arena Web-app Agent: 1289 Elo2026-08-22
Design Arena Web-app Agent: 1290 Elo2026-08-23
Design Arena Web-app Agent: 1279 Elo2026-08-28
Design Arena Web-app Agent: 1284 Elo2026-08-24
Design Arena Web-app Agent: 1282 Elo2026-08-25
Design Arena Web-app Agent: 1282 Elo2026-08-26
Design Arena Web-app Agent: 1279 Elo2026-09-06
Design Arena Web-app Agent: 1279 Elo2026-08-29
Design Arena Web-app Agent: 1279 Elo2026-08-30
Design Arena Web-app Agent: 1279 Elo2026-08-31
Design Arena Web-app Agent: 1279 Elo2026-09-01
Design Arena Web-app Agent: 1279 Elo2026-09-02
Design Arena Web-app Agent: 1279 Elo2026-09-03
Design Arena Web-app Agent: 1279 Elo2026-09-04
Design Arena Website: 1320 Elo2026-07-28
Design Arena Website: 1320 Elo2026-07-27
Design Arena Website: 1320 Elo2026-07-30
Design Arena Website: 1320 Elo2026-07-29
Design Arena Website: 1319 Elo2026-07-31
Design Arena Website: 1319 Elo2026-08-02
Design Arena Website: 1319 Elo2026-08-01
Design Arena Website: 1319 Elo2026-08-05
Design Arena Website: 1318 Elo2026-08-03
Design Arena Website: 1317 Elo2026-08-09
Design Arena Website: 1319 Elo2026-08-04
Design Arena Website: 1314 Elo2026-08-14
Design Arena Website: 1318 Elo2026-08-06
Design Arena Website: 1318 Elo2026-08-07
Design Arena Website: 1317 Elo2026-08-10
Design Arena Website: 1317 Elo2026-08-08
Design Arena Website: 1307 Elo2026-08-18
Design Arena Website: 1317 Elo2026-08-11
Design Arena Website: 1307 Elo2026-08-15
Design Arena Website: 1317 Elo2026-08-12
Design Arena Website: 1315 Elo2026-08-13
Design Arena Website: 1307 Elo2026-08-19
Design Arena Website: 1306 Elo2026-08-16
Design Arena Website: 1307 Elo2026-08-20
Design Arena Website: 1315 Elo2026-08-27
Design Arena Website: 1307 Elo2026-08-17
Design Arena Website: 1309 Elo2026-09-05
Design Arena Website: 1315 Elo2026-08-21
Design Arena Website: 1315 Elo2026-08-22
Design Arena Website: 1315 Elo2026-08-23
Design Arena Website: 1315 Elo2026-08-24
Design Arena Website: 1315 Elo2026-08-28
Design Arena Website: 1316 Elo2026-08-25
Design Arena Website: 1316 Elo2026-08-26
Design Arena Website: 1307 Elo2026-09-06
Design Arena Website: 1315 Elo2026-08-29
Design Arena Website: 1314 Elo2026-08-30
Design Arena Website: 1314 Elo2026-08-31
Design Arena Website: 1314 Elo2026-09-01
Design Arena Website: 1314 Elo2026-09-02
Design Arena Website: 1311 Elo2026-09-03
Design Arena Website: 1310 Elo2026-09-04
LiveBench Agentic Coding: 50.7%2026-06-25
LiveBench Coding: 82.1%2026-06-25
LiveBench Data Analysis: 78.3%2026-06-25
LiveBench Instruction Following: 66.7%2026-06-25
LiveBench Language: 77.9%2026-06-25
LiveBench Math: 92.8%2026-06-25
LiveBench Reasoning: 87.2%2026-06-25
LMArena Agent: 7.72026-07-13
LMArena Agent: 8.32026-07-20
LMArena Agent: 8.12026-07-27
LMArena Agent: 7.92026-07-21
LMArena Agent: 8.22026-07-28
LMArena Agent: 8.32026-08-06
LMArena Agent: 8.22026-08-03
LMArena Agent: 8.22026-08-12
LMArena Agent: 8.22026-08-11
LMArena Agent: 8.22026-08-13
LMArena Agent: 7.32026-08-24
LMArena Agent: 6.62026-08-31
LMArena Agent: 62026-09-05
LMArena Agent: 72026-08-27
LMArena Creative Writing: 1484 Elo2026-07-21
LMArena Creative Writing: 1484 Elo2026-07-27
LMArena Creative Writing: 1484 Elo2026-07-30
LMArena Creative Writing: 1483 Elo2026-08-02
LMArena Creative Writing: 1483 Elo2026-08-03
LMArena Creative Writing: 1485 Elo2026-08-06
LMArena Creative Writing: 1486 Elo2026-08-12
LMArena Creative Writing: 1486 Elo2026-08-21
LMArena Creative Writing: 1485 Elo2026-09-02
LMArena Creative Writing: 1485 Elo2026-08-27
LMArena Creative Writing: 1485 Elo2026-09-01
LMArena Instruction Following: 1497 Elo2026-07-21
LMArena Instruction Following: 1498 Elo2026-07-27
LMArena Instruction Following: 1498 Elo2026-07-30
LMArena Instruction Following: 1497 Elo2026-08-02
LMArena Instruction Following: 1497 Elo2026-08-03
LMArena Instruction Following: 1497 Elo2026-08-06
LMArena Instruction Following: 1498 Elo2026-08-12
LMArena Instruction Following: 1498 Elo2026-08-21
LMArena Instruction Following: 1498 Elo2026-09-02
LMArena Instruction Following: 1497 Elo2026-08-27
LMArena Instruction Following: 1498 Elo2026-09-01
LMArena Long Query: 1505 Elo2026-07-21
LMArena Long Query: 1506 Elo2026-07-27
LMArena Long Query: 1506 Elo2026-07-30
LMArena Long Query: 1505 Elo2026-08-02
LMArena Long Query: 1505 Elo2026-08-03
LMArena Long Query: 1505 Elo2026-08-06
LMArena Long Query: 1505 Elo2026-08-12
LMArena Long Query: 1505 Elo2026-08-21
LMArena Long Query: 1505 Elo2026-09-02
LMArena Long Query: 1505 Elo2026-08-27
LMArena Long Query: 1505 Elo2026-09-01
LMArena Math: 1500 Elo2026-07-21
LMArena Math: 1499 Elo2026-07-27
LMArena Math: 1499 Elo2026-07-30
LMArena Math: 1498 Elo2026-08-02
LMArena Math: 1498 Elo2026-08-03
LMArena Math: 1498 Elo2026-08-06
LMArena Math: 1498 Elo2026-08-12
LMArena Math: 1498 Elo2026-08-21
LMArena Math: 1498 Elo2026-08-27
LMArena Math: 1498 Elo2026-09-01
LMArena Text: 1490 Elo2026-07-16
LMArena Text: 1499 Elo2026-07-20
LMArena Text: 1502 Elo2026-07-21
LMArena Text: 1502 Elo2026-07-27
LMArena Text: 1502 Elo2026-07-30
LMArena Text: 1502 Elo2026-08-02
LMArena Text: 1502 Elo2026-08-06
LMArena Text: 1502 Elo2026-08-03
LMArena Text: 1502 Elo2026-08-12
LMArena Text: 1502 Elo2026-08-10
LMArena Text: 1502 Elo2026-08-21
LMArena Text: 1502 Elo2026-09-01
LMArena Text: 1502 Elo2026-09-02
LMArena Text: 1502 Elo2026-08-27
LMArena Vision: 1318 Elo2026-07-12
LMArena Vision: 1306 Elo2026-07-21
LMArena Vision: 1304 Elo2026-07-26
LMArena Vision: 1304 Elo2026-07-30
LMArena Vision: 1303 Elo2026-08-02
LMArena Vision: 1301 Elo2026-08-06
LMArena Vision: 1301 Elo2026-08-21
LMArena Vision: 1301 Elo2026-08-27
LMArena WebDev: 1558 Elo2026-07-16
LMArena WebDev: 1559 Elo2026-07-21
LMArena WebDev: 1559 Elo2026-07-20
LMArena WebDev: 1560 Elo2026-07-27
LMArena WebDev: 1559 Elo2026-07-24
LMArena WebDev: 1560 Elo2026-07-28
LMArena WebDev: 1560 Elo2026-07-30
LMArena WebDev: 1561 Elo2026-08-01
LMArena WebDev: 1560 Elo2026-07-31
LMArena WebDev: 1560 Elo2026-08-06
LMArena WebDev: 1561 Elo2026-08-02
LMArena WebDev: 1558 Elo2026-08-10
LMArena WebDev: 1558 Elo2026-08-12
LMArena WebDev: 1558 Elo2026-08-14
LMArena WebDev: 1557 Elo2026-09-01
LMArena WebDev: 1557 Elo2026-09-05
LMArena WebDev: 1558 Elo2026-08-21
LMArena WebDev: 1557 Elo2026-08-30
OSWorld Verified^‡: 18.2%2026-06-24max effort
SWE-rebench^‡: 53.1% ± 1.52026-05-15tools
Terminal-Bench 2.1^‡: 68.9% ± 1.42026-05-01max effort

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

Best LLM for Competition MathEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Business WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Logic & Problem SolvingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Marketing CopyEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Chat & RoleplayEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Creative WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Frontend & UIEstablished evidence
100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Roleplay & CharacterEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for a General AssistantEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Computer & Browser UseEstablished evidence
90% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
Best LLM for Agentic CodingEstablished evidence
86% of intended weighted task evidence across 5 independent sources. 8 of 8 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
84% of intended weighted task evidence across 5 independent sources. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Autonomous AgentsEstablished evidence
82% of intended weighted task evidence across 5 independent sources. 7 of 7 configured evaluation feeds currently have results.
Best LLM for Code CompletionEstablished evidence
81% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
Best LLM for Debugging & Code ReviewEstablished evidence
70% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best LLM for AI AgentsEstablished evidence
70% of intended weighted task evidence across 5 independent sources. 7 of 7 configured evaluation feeds currently have results.
Best Open-Weight LLM for Self-HostingEstablished evidence
67% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Image UnderstandingEstablished evidence
65% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best Local LLM for CodingEstablished evidence
64% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Fast SummariesEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best Value LLMEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Hermes AgentEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Document SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 configured evaluation feeds currently have results.
Best LLM for SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 configured evaluation feeds currently have results.
Best LLM for Literary TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Everyday TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best LLM for TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best Cheap LLM for High VolumeProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
Cheapest Capable LLMProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Massive ContextProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 3 of 4 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LongBench v2. 4 of 6 configured evaluation feeds currently have results.
Best LLM for OCR & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for JSON & Schema OutputProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Tool & Function CallingProvisional evidence
35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for High-Volume ExtractionProvisional evidence
31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 2 of 4 configured evaluation feeds currently have results.
Best LLM for Grounded RAGProvisional evidence
30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.